Non Symbolic AI - Lecture 14

1. Non Symbolic AI - Lecture14 Final Lecture. Exam/coursework advice + more on Neutral Networks + robot videos Non Symbolic AI Lecture 14

2. What should you write in the coursework writeup? Firstly, your program code should be clear and commented – so the writeup should not just be a further description of the code Secondly, even if your code does not work as you had hoped, you can still gain marks from a good writeup Non Symbolic AI Lecture 14

3. Demonstrate your understanding! We want to see that you understand the basics of ANNs, what they can be used for. The basics of a learning algorithm such as backprop The basicsof a GA The basics of applying an ANN to a Boolean problem such as this. Non Symbolic AI Lecture 14

4. Use your own words Straight repetition from the lecture notes or a textbook is a bad idea! It suggests that you have memorised the words without understanding them. Your own way of describing things will be much more impressive! Non Symbolic AI Lecture 14

5. Did you think beyond the problem? Was the problem a sensible one? Was backprop a sensible learning algorithm? Was a GA a sensible idea? Would you expect all problems to be like this one, or different? Non Symbolic AI Lecture 14

6. Did you think beyond your results? Are you happy with your results? Why? Were you lucky, or unlucky? If you did it again once, or many times, would you expect the same answers? Why/why not? The more intelligent comments that you can make, the better. Non Symbolic AI Lecture 14

7. Don’t leave it to the last minute! You should aim to basically finish – and print out your submission – at least 1, pref 2 days before the deadline. For some amazing reason, computers and printers break down just before a deadline – it is your responsibility to anticipate this! Then with good luck, you may think of some improvements in the last 2 days for a better version – but you are not relying on good luck. Non Symbolic AI Lecture 14

8. Exam technique -- Revision The Exam is due on [announce date] June. Pointers to previous exam pages via the course web page. 90 minutes, choose Two out of Three questions. Third optional question is an essay question, with several possible titles given. Non Symbolic AI Lecture 14

9. Advice Taken from:- www.informatics.sussex.ac.uk/doc/unseen_exams.php Revise Non-Sym AI alongside the other courses A > B > C > NSAI > A > B > C > NSAI > A > B > …. Non Symbolic AI Lecture 14

10. Revision is done by Writing! Take your lecture notes, or textbook or any written material you want to revise – and write notes in your own words to summarise what is said. Input Information usually doesn’t stick in your brain unless you output something from it – and writing notes is the best way. Non Symbolic AI Lecture 14

11. Summarise in notes First time round, just summarise a paper or a lecture into just a page or two. Then start again: see if you can summarise your summary into less than a page. Then start again: see if you can summarise your new summary into a small postcard – in all this, the summarising makes sense of it, the writing makes it stick! Non Symbolic AI Lecture 14

12. Practice an Exam Take an old NSAI exam – lock yourself in a room for 90 minutes – and see how well you do. Read the questions. Manage your time. Don't spend so much time answering your 'favourite question' that you can write only scrappy notes for the other question you choose. Non Symbolic AI Lecture 14

13. Answering a question Plan each answer. Jot down a skeleton answer-plan, on a page which you will cross out as rough work. Especially important for an Essay-answer. Answer the question on the exam paper - not the one you were expecting to find on the paper. Check how many points are allocated for each part of a multi-part question – and allocate your time accordingly Use any spare time to re-read your answers, and improve them Non Symbolic AI Lecture 14

14. Before the Exam Do your revision in good time – finish a couple of days before the exam Then come out of your hole, take a break, get some exercise, get a good night’s sleep before the exam. … and Don’t Worry … ! Non Symbolic AI Lecture 14

15. Bit more on Neutral Networks (Followed by some robot videos) Basics of Neutral Networks covered in last lecture. Here (at high speed) is a reprise of that, plus a bit more. Non Symbolic AI Lecture 14

16. Genetic Convergence is not Stasis B is the point of convergence (defn 2), often after 'punctuated equilibria' A is the point of genetic convergence (defn 1), which may well be (surprisingly?) within the first 10 or so generations ! Non Symbolic AI Lecture 14

17. Optimal mutation rates Continuing SAGA ideas, in a fitness landscape you can have too little mutation (relative to selection:- Non Symbolic AI Lecture 14

18. … or too much mutation … or you can have too much mutation … (arrow up the hill is selection, arrow down the hill is mutation) Non Symbolic AI Lecture 14

19. … or just about the right amount … ... or you can gave round about the right amount, to avoid losing height (fitness) gained, but promoting search along ridges -- which may lead to higher ground :- Balance between exploration and exploitation Non Symbolic AI Lecture 14

20. Why should there be an optimal mut-rate? Mutation rate too low, in limit zero, would mean no further change, evolution ceases -> no good Mutation rate too high, eg every bit flipped at random, implies random search -> no good. Non Symbolic AI Lecture 14

21. High dimensional landscapes We can visualise ridges in the 3-D landscapes (Himalayas, South Downs) that the metaphor of fitness landscapes draws upon. But in 100-D or 1000-D landscapes things can be very significantly different. In particular you can have ridges in all sorts of directions. Non Symbolic AI Lecture 14

22. Ridges in high-dimensional landscapes Going from 2-D to 3-D allows extra opportunities for “bypasses around a valley without dropping height” Going up to 100-D or 1000-D potentially allows many many more such opportunities -- hyper-dimensional bypasses. (pic borrowed from Steps Towards Life, Manfred Eigen Oxford Univ Press 1992) Non Symbolic AI Lecture 14

23. The New Picture IF there is lots of neutrality of the right kind, then there are lots of Neutral Networks, connected pathways of neutral mutations running through the landscape at one level -- Non Symbolic AI Lecture 14

24. Right kind of redundancy • Multi-storey building example – some corridors lead to staircases • When this is so, ‘going along the flat’ buys you something • Of course, if corridors lead to flat plains without a staircase in sight, you are wasting your time! Non Symbolic AI Lecture 14

25. The First claim for Neutral Networks (1) The Formal claim It can be demonstrated indisputably thatIF a fitness landscape has lots of neutrality of a certain kind, giving rise to Neutral Networks with the property of constant innovation THEN the dynamics of evolution will be transformed (as compared to landscapes without neutrality) and in particular populations will not get stuck on local optima. The above would be merely a mathematical curiosity unless you can also accept:- Non Symbolic AI Lecture 14

26. The Second claim for Neutral Networks (2) The Empirical claim Many difficult real design problems (..the more difficult the better...) in eg evolutionary robotics, evolvable hardware, drug design --- have fitness landscapes that naturally (ie without any special effort) fit the bill for (1) above. I make claim (2), but admit it is as yet a dodgy claim! Recently some supporting evidence. Non Symbolic AI Lecture 14

27. Recent Research on Neutral Networks One of the first demonstrations of the formal claim was in an EASy MSc dissertation by Lionel Barnett 1997. See full dissertation, and shorter version for Alife98 conference, on his web pages http://www.cogs.susx.ac.uk/users/lionelb/ and Neutral Network bibliography via http://www.cogs.susx.ac.uk/lab/adapt/nn.html Non Symbolic AI Lecture 14

28. The New Picture IF there is lots of neutrality of the right kind, then there are lots of Neutral Networks, connected pathways of neutral mutations running through the landscape at one level -- Non Symbolic AI Lecture 14

29. … percolation … -- and lots and lots of these NNs, at different levels, percolating through the whole of genotype space, passing close to each other in many places. Without such neutrality, if you are stuck at a local optimum (ie no nbrs higher) then there are only N nbrs to look at BUT WHEN you have lots of neutrality, then without losing fitness you can move along a NN, with nearly N new nbrs at every step -- 'constant innovation'. Basically, you never get stuck ! Non Symbolic AI Lecture 14

30. Right kind of redundancy • Multi-storey building example – some corridors lead to staircases • When this is so, ‘going along the flat’ buys you something • Of course, if corridors lead to flat plains without a staircase in sight, you are wasting your time! Non Symbolic AI Lecture 14

31. What happens? Roughly speaking, in such a landscape the population will quickly 'climb onto' a ridge slightly higher than average, then move around neutrally 'looking for a higher nbr to jump to'. You might have to wait a while (even a long while...) but you will not get stuck for ever. When eventually one of the popn finds a higher NN, the popn as a whole 'hops up‘ and carries on searching as before Non Symbolic AI Lecture 14

32. Punk Eek ...and significantly, in many real GA problems this is just the sort of pattern that you see. The horizontal bits are not (as many thought) just standing still waiting for luck --- rather 'running along NNs waiting for luck' Non Symbolic AI Lecture 14

33. Ruggedness versus Neutrality Lionel Barnett's NKp landscape gives an abstract framework in which one can tune independently: K for ruggedness and p for degree of Neutrality. There are various standard measures for ruggedness e.g. autocorrelation -- roughly, a measure of how closely related in height are points 1 apart, 2 apart, ...10 apart... Amazingly, for fixed N and K, when you tune parameter p all the way from zero neutrality up to maximum neutrality the autocorrelation remains (virtually) unchanged. Non Symbolic AI Lecture 14

34. Same ruggedness but different dynamics Yet as you change the neutrality p, despite having the same ruggedness the evolutionary dynamics changes completely -- for zero neutrality the population gets easily stuck on local optima, for high neutrality it does not. Clearly neutrality makes a big difference -- yet this has been completely unknown to the GA community, who have only worried about ruggedness. Indeed all the typical benchmark problems used to compare different GAs have no neutrality at all. Non Symbolic AI Lecture 14

35. Net-crawlers • The EH example was basically a bastardised version of a GA – a net-crawler –equivalent to a Steady-state GA with population size 2. • Lionel Barnett, in his thesis, showed that for a particular class of abstract fitness landscape (epsilon-correlated) that had many NNs, s.t. that the population could jump from one to the next, then provably the best search method was a net-crawler with a specific rate of mutation Non Symbolic AI Lecture 14

36. Net-crawling mutation rate • Optimal rate is provably (under certain assumptions):- • Mutate exactly n (an integer) bits on genotype • … where n is chosen so as to make the percentage of neutral mutations as close as possible to 37% (1/e) • (using plausible assumptions) this can be calculated on the fly, keeping track of how many recent mutations were neutral and adjusting mutation up/down accordingly • For the EH example, this looks like suggesting 3 mutations !!! Non Symbolic AI Lecture 14

37. Summary on NNs Please distinguish between The FORMAL claim, proven without doubt: that fitness landscapes full of neutral networks of the right kind completely alter evolutionary dynamics The EMPIRICAL claim, that many real-world difficult design problems, with (near-)binary encodings, do in fact have lots of neutral networks of the right kind. Non Symbolic AI Lecture 14

38. When building robots, the Classical AI approach has the robot as a scientist-spectator, seeking information from outside. "SMPA" -- so-called by Brooks (1999) S sense M model P plan A action Classical AI Non Symbolic AI Lecture 14

39. Shakey 1970-Shakey the robot reasons about its blocksBuilt at Stanford Research Institute, Shakey was remote controlled by a large computer. It hosted a clever reasoning program fed very selective spatial data, derived from weak edge-based processing of camera and laser range measurements. On a very good day it could formulate and execute, over a period of hours, plans involving moving from place to place and pushing blocks to achieve a goal. Courtesy of SRI International. Non Symbolic AI Lecture 14

40. The Honda Humanoid Robot Non Symbolic AI Lecture 14

41. Honda Non Symbolic AI Lecture 14

42. Brooks’ alternative Brooks’ alternative is in terms of many individual and largely separate behaviours – where any one behaviour is generated by a pathway in the ‘brain’ or control system all the way from Sensors to Motors. No Central Model, or Central Planning system. Non Symbolic AI Lecture 14

43. Sojourner Rover on Mars NASA and JPL July 1997 Based heavily on Brook’s ideas “Fast cheap and out of control!” Non Symbolic AI Lecture 14

44. Sojourner Non Symbolic AI Lecture 14

45. Sojourner Semi-autonomous Signals from Earth took around 30 minutes to reach Mars Non Symbolic AI Lecture 14

46. Subsumption summary • New philosophy of hand design of robot control systems • Incremental engineering – debug simpler versions first • Robots must work in real time in the real world • Spaghetti-like systems unclear for analysis • Not clear if behaviours can be re-used • Scaling – can it go more than 12 behaviours? Non Symbolic AI Lecture 14

47. Over rough terrain Non Symbolic AI Lecture 14

48. For military or rescue Non Symbolic AI Lecture 14

49. For military or rescue Non Symbolic AI Lecture 14

50. Underwater Non Symbolic AI Lecture 14